3 Sequencing data

3.1 Sequencing depth

tibble(metric=c("Total GB", "Total reads", "Average GB", "Average reads"),
       value=unlist(c(round(all_data %>% summarise(sum(bases_pre_fastp)) / 1000000000,2),
               round(all_data %>% summarise(sum(bases_pre_fastp)) / 300,2),
               paste0(round(all_data %>% summarise(mean(bases_pre_fastp)) / 1000000000,2),"±",round(all_data %>% summarise(sd(bases_pre_fastp)) / 1000000000,2)),
               paste0(round(all_data %>% summarise(mean(bases_pre_fastp)) / 300,0),"±",round(all_data %>% summarise(sd(bases_pre_fastp)) / 300,0))))
       ) %>%
  tt()

metric	value
Total GB	937.37
Total reads	3124578099
Average GB	5.18±2.46
Average reads	17262862±8195554

all_data %>%
    group_by(Taxon,Extraction) %>%
    summarise(value = sprintf("%.1f±%.1f", mean(bases_post_fastp / 1000000000), sd(bases_post_fastp / 1000000000))) %>%
    pivot_wider(names_from = Extraction, values_from = value) %>%
    tt(caption = "Mean and standard deviation of sequencing depth (GB)")

Mean and standard deviation of sequencing depth (GB)

Taxon	DREX	EHEX	ZYMO
Amphibian	3.2±2.1	4.7±0.3	4.0±1.6
Bird	4.2±2.4	3.1±1.9	3.9±1.8
Control	0.5±0.6	2.1±2.7	0.0±0.0
Mammal	4.6±2.0	3.8±2.2	5.4±3.2
Reptile	5.7±1.3	5.0±1.8	6.1±2.2

all_data %>%
    ggplot(aes(x=Extraction,y=bases_pre_fastp))+ 
        geom_boxplot() + 
        facet_grid(. ~ Taxon, scales = "free") +
        labs(y="DNA yield (ng)",x="Extraction method")

all_data  %>%
    filter(Taxon != "Control") %>%
    lmerTest::lmer(bases_post_fastp ~ Extraction + (1 | Sample) + (1 | Species), data = ., REML = FALSE) %>%
    broom.mixed::tidy() %>%
    tt()

effect	group	term	estimate	std.error	statistic	df	p.value
fixed	NA	(Intercept)	4322719741	382290022	11.30743545	1.711860e+01	2.299227e-09
fixed	NA	ExtractionEHEX	10864597	284400639	0.03820173	1.443429e+09	9.695268e-01
fixed	NA	ExtractionZYMO	485437083	283030980	1.71513762	4.313942e+21	8.632000e-02
ran_pars	Sample	sd__(Intercept)	1407267694	NA	NA	NA	NA
ran_pars	Species	sd__(Intercept)	508228833	NA	NA	NA	NA
ran_pars	Residual	sd__Observation	1524168473	NA	NA	NA	NA

3.2 Quality-filtering

all_data %>%
    mutate(qf_bases=bases_post_fastp/bases_pre_fastp*100) %>%
    group_by(Taxon,Extraction) %>%
    summarise(value = sprintf("%.1f±%.1f", mean(qf_bases), sd(qf_bases))) %>%
    pivot_wider(names_from = Extraction, values_from = value) %>%
    tt(caption = "Mean and standard deviation of quality-filtered proportion of reads")

Mean and standard deviation of quality-filtered proportion of reads

Taxon	DREX	EHEX	ZYMO
Amphibian	91.7±3.7	87.6±2.9	84.7±1.2
Bird	70.3±23.0	70.2±14.7	70.9±16.1
Control	9.8±11.5	27.5±3.4	3.3±2.3
Mammal	89.5±4.7	91.2±1.9	91.9±2.3
Reptile	90.5±7.1	88.3±7.2	89.9±6.3

all_data %>%
    mutate(qf_bases=bases_post_fastp/bases_pre_fastp*100) %>%
    ggplot(aes(x=Extraction,y=qf_bases))+ 
        geom_boxplot() + 
        facet_grid(. ~ Taxon, scales = "free") +
        labs(y="DNA yield (ng)",x="Extraction method")

all_data  %>%
    mutate(qf_bases=bases_post_fastp/bases_pre_fastp*100) %>%
    filter(Taxon != "Control") %>%
    lmerTest::lmer(qf_bases ~ Extraction + (1 | Sample) + (1 | Species), data = ., REML = FALSE) %>%
    broom.mixed::tidy() %>%
    tt()

effect	group	term	estimate	std.error	statistic	df	p.value
fixed	NA	(Intercept)	84.867885	3.229677	26.2775145	12.92142	1.337096e-12
fixed	NA	ExtractionEHEX	-1.238440	1.268390	-0.9763877	145.71392	3.304905e-01
fixed	NA	ExtractionZYMO	-1.811218	1.262245	-1.4349184	145.69071	1.534536e-01
ran_pars	Sample	sd__(Intercept)	7.418801	NA	NA	NA	NA
ran_pars	Species	sd__(Intercept)	9.356829	NA	NA	NA	NA
ran_pars	Residual	sd__Observation	6.797395	NA	NA	NA	NA